A multi-objective collaborative intelligent driving test scenario operation adjustment control method

Abstract

The present invention relates to the technical field of driving test scene control, and discloses a multi-objective collaborative intelligent driving test scene operation adjustment control method, the method comprising: collecting real road map data, identifying key road areas; selecting corresponding key road areas according to test objectives, and clustering and fusing key road areas; obtaining the driving trajectory of the test vehicle on the fusion test scene road; and dynamically alternatingly regulating the driving speed of the test vehicle on the driving trajectory. The present invention combines the heading angle and heading angle change rate of the road nodes in the road, calculates the road information that characterizes the road form and complexity, uses the road information as the type of the road, realizes the extraction of different types of key road areas, and constructs a fusion test scene road that meets the test objective requirements, constructs a driving trajectory planning objective function based on multi-objective costs, and dynamically regulates the vehicle speed according to the various characteristics of different trajectory segments.

Description

Technical Field

[0001] The present invention relates to the technical field of driving test scene control, and in particular to a multi-objective collaborative intelligent driving test scene operation adjustment control method. Background Art

[0002] The development of intelligent driving technology is inseparable from an efficient testing and verification process. As autonomous driving technology matures, single-target test scenarios can no longer meet the requirements for system comprehensiveness. Intelligent driving testing not only needs to verify the basic functions and safety of a vehicle in a single scenario, but also needs to evaluate its coordinated performance among multiple objectives (such as safety, comfort, energy efficiency, etc.) in a complex traffic environment. It is necessary to conduct simultaneous tests on multiple different road types in the same road scenario. Summary of the invention

[0003] In view of this, the present invention proposes a multi-objective collaborative intelligent driving test scenario operation adjustment and control method, which adjusts and controls the operating state of the vehicle by simultaneously considering multiple target requirements in the test scenario, thereby comprehensively evaluating the performance of the intelligent driving system, helping to improve the comprehensiveness and reliability of the test, and discovering potential problems and deficiencies.

[0004] To achieve the above object, the present invention provides a multi-objective coordinated intelligent driving test scenario operation adjustment control method, comprising the following steps:

[0005] S1: Collect real road map data and identify key road areas to obtain different types of key road areas;

[0006] Collect real road map data, wherein the collected real road map data is represented in the form of:

[0007] ;

[0008] ;

[0009] ;

[0010] ;

[0011] in:

[0012] Indicates the collected real road map data;

[0013] Displays real road map data The initial set of roads in Represents the initial road set The nth initial road in, N represents the initial road set The total number of initial roads in ; the initial roads refer to roads without intersections in the middle of the roads;

[0014] Displays real road map data The set of intersection locations in , Represents a set of intersection locations The mth intersection position in, M represents the intersection position set The total number of intersection locations in ;

[0015] Indicates the initial road In road nodes, among which Indicates the initial road The starting point in Indicates the initial road The end point in the road node includes the turning point and the starting and ending points of the road;

[0016] For the initial road set The initial roads in the image are used to identify the key road areas, and different types of key road areas are obtained;

[0017] S2: Select the corresponding key road area according to the test target, and perform clustering fusion of the key road areas to obtain the fusion test scene road;

[0018] S3: according to the starting and ending points of the test vehicle in the fusion test scene road and the fusion test scene road, estimating the driving trajectory of the test vehicle on the fusion test scene road;

[0019] S4: According to the calculated driving trajectory of the test vehicle, dynamically and alternately adjust the driving speed of the test vehicle on the driving trajectory.

[0020] As a further improvement method of the present invention:

[0021] Optionally, in step S1, the initial road set The initial road in the process of identifying key road areas includes:

[0022] For the initial road set The critical road area is identified by the initial road in the image. The critical road area identification process is as follows:

[0023] S11: The initial roads whose road lengths are higher than the preset road length threshold are regarded as key road areas to form a key road area set. :

[0024] ;

[0025] ;

[0026] in:

[0027] represents the g-th critical road area, and G represents the total number of critical road areas;

[0028] Indicates critical road areas In road nodes;

[0029] S12: Calculate the critical road area set The road node heading angle sequence of any key road area in The road node heading angle sequence is:

[0030] ;

[0031] ;

[0032] in:

[0033] Indicates critical road areas The road node heading angle sequence;

[0034] Indicates critical road areas The i-th road node The X-axis coordinate value in the Mercator coordinate system, Indicates critical road areas The i-th road node The Y-axis coordinate value in the Mercator coordinate system, ;

[0035] Indicates critical road areas The i-th road node The heading angle of the road node;

[0036] In an embodiment of the present invention, ;

[0037] S13: Calculate the key road area set The heading angle change rate sequence of any key road area in The heading angle change rate sequence is:

[0038] ;

[0039] ;

[0040] in:

[0041] Indicates critical road areas The heading angle change rate sequence;

[0042] Indicates critical road areas The i-th road node The rate of change of heading angle;

[0043] Indicates critical road areas The i-th road node In key road areas The relative position of the i-th road node Along key road areas To starting point distance;

[0044] S14: Constitutes a critical road area Road information:

[0045] ;

[0046] ;

[0047] in:

[0048] Indicates critical road areas Road information;

[0049] Indicates critical road areas The heading angle change information, Represents the heading angle change rate sequence The number of road nodes above the preset change rate threshold, as well as Indicates critical road areas If both are close to 0, it means the critical road area is the straight road area. The larger the two are, the more critical the road area is. The higher the degree of curvature and complexity;

[0050] Indicates critical road areas The relative position change sequence.

[0051] Optionally, selecting a corresponding key road area according to a test target in step S2 includes:

[0052] Generate the test target of the driving test scenario, where the test target includes the road form and complexity of the test scenario. The road form includes straight roads and curved roads. Select the corresponding key road area according to the test target. The selected key road area set is:

[0053] ;

[0054] in:

[0055] represents the dth key road area selected, and D represents the total number of key road areas selected;

[0056] Key road areas The road information is ;

[0057] The selected key road areas are clustered and fused to obtain a fused test scene road.

[0058] Optionally, clustering and fusing the selected key road areas to obtain a fused test scene road includes:

[0059] The selected key road areas are clustered and fused to obtain the fused test scene roads, where the clustering fusion process is as follows:

[0060] S21: Calculate the road node correlation distance between any two selected key road areas, where the key road area and The road node association distance is:

[0061] ;

[0062] in:

[0063] Indicates critical road areas and The road node association distance;

[0064] Represents a road node The Euclidean distance between Indicates critical road areas The Road nodes, Indicates critical road areas The road nodes;

[0065] Indicates critical road areas The total number of road nodes in , Indicates critical road areas The total number of road nodes in ;

[0066] S22: Calculate the road information distance between any two selected key road areas, where the key road area and The road information distance is:

[0067] ;

[0068] in:

[0069] Indicates critical road areas and Road information distance;

[0070] represents the L2 norm;

[0071] represents an exponential function with a natural constant as base;

[0072] S23: Construct the distance between any two selected key road areas, where the key road area and The distance is:

[0073] ;

[0074] in:

[0075] Indicates critical road areas and distance;

[0076] S24: Based on the distance between the key road areas, a clustering algorithm is used to cluster the selected D key road areas to obtain U road clusters, the mean of the road node association distance between any two key road areas in any road cluster is calculated, the road cluster with the smallest mean of the road node association distance is selected, and all the key road areas in the selected road cluster are used as the fusion test scene road load. In the embodiment of the present invention, the clustering algorithm used is a hierarchical clustering algorithm.

[0077] Optionally, in step S3, generating a driving trajectory of the test vehicle according to the starting and ending points of the test vehicle in the fused test scene road and the fused test scene road includes:

[0078] According to the starting and ending points of the test vehicle in the fusion test scene road and the fusion test scene road, the test vehicle driving trajectory is generated, wherein the driving trajectory planning process of the test vehicle on the fusion test scene road Load is as follows:

[0079] S31: Obtain road node information of the fusion test scenario road Load:

[0080] ;

[0081] in:

[0082] Represents the K road node information of the fusion test scenario road load;

[0083] S32: Construct the driving trajectory planning objective function:

[0084] ;

[0085] ;

[0086] ;

[0087] ;

[0088] ;

[0089] in:

[0090] represents the driving trajectory planning objective function, and H represents the driving trajectory of the test vehicle to be solved;

[0091] They represent the path similarity cost, compact cost, trajectory smoothness cost and collision cost of the test vehicle's driving trajectory H respectively;

[0092] Indicates the coordinate position of the kth road node in the fusion test scene road Load, Represents the uth track point in the test vehicle's driving track H The coordinate position of Indicates coordinate position The X-axis coordinate in Indicates coordinate position The Y-axis coordinate in;

[0093] Indicates coordinate position The Euclidean distance between

[0094] represents the adjustment coefficient, Set to 10;

[0095] Indicates coordinate position The Euclidean distance to the nearest obstacle in the fusion test scene road Load, Indicates the preset maximum obstacle impact distance;

[0096] S33: Planning the objective function of the driving trajectory Perform optimization and solve to obtain the test vehicle's driving trajectory .

[0097] Optionally, in the step S33, the target function of the driving trajectory planning is Perform optimization solutions, including:

[0098] S331: Generate driving trajectory planning objective function Constraints:

[0099] ;

[0100] in:

[0101] represents the trajectory deviation threshold of the test vehicle's driving trajectory;

[0102] S332: Initialize and generate a set of test vehicle driving trajectories , and the iteration coefficient ;

[0103] S333: Set the current iteration number to t, the maximum iteration number to Max, and the initial value of t to 0. Then the t-th iteration results of the test vehicle driving trajectory and iteration coefficient are ;

[0104] in: It represents the iteration coefficient of the t-th iteration, which is used to control the driving trajectory objective function of the t-th iteration;

[0105] S334: Reconstruct the driving trajectory planning objective function based on the constraint conditions, where the reconstruction result is:

[0106] ;

[0107] in:

[0108] Indicates the test vehicle's driving trajectory The coordinate position of the u-th trajectory point in ;

[0109] The reconstructed Find the minimum value and obtain the test vehicle driving trajectory that minimizes the reconstruction result ;

[0110] S335: If is less than the preset threshold, then The final solution for the test vehicle driving trajectory , otherwise let , t=t+1, return to step S334, where represents the coefficient iteration step size, Set to 0.1, Represents the iteration coefficient of the t+1th iteration.

[0111] Optionally, in step S4, dynamically and alternately regulating the driving speed of the test vehicle on the driving track includes:

[0112] The test vehicle is on the driving track The driving speed on the vehicle is dynamically alternatingly regulated, wherein the dynamic alternating regulation process is as follows:

[0113] S41: Obtaining the driving trajectory of the test vehicle Trajectory path segments in :

[0114] ;

[0115] in:

[0116] Indicates the test vehicle's driving trajectory The kth trajectory path segment in , that is, the test vehicle driving trajectory The kth trajectory point and the k+1th trajectory point The trajectory path between

[0117] S42: Calculate the path length, heading angle change information and number of obstacles of each trajectory path segment. The heading angle change information is , the number of obstacles affecting is ; The trajectory path segment The heading angle change information is the trajectory point Testing vehicle driving trajectory The heading angle change rate in the trajectory path segment The influencing obstacle in is the trajectory path segment The driving trajectory of the test vehicle The distance between The number of obstacles;

[0118] S43: Generate a test vehicle driving trajectory Dynamically control the driving speed of different trajectory path segments, where the trajectory path segment The dynamic control driving speed is:

[0119] ;

[0120] in:

[0121] Represents a trajectory path segment Dynamically control driving speed.

[0122] In order to solve the above problem, the present invention provides an electronic device, the electronic device comprising:

[0123] A memory storing at least one instruction;

[0124] Communication interface, enabling electronic equipment to communicate; and

[0125] A processor executes instructions stored in the memory to implement the above-mentioned multi-objective collaborative intelligent driving test scenario operation adjustment control method.

[0126] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned multi-objective collaborative intelligent driving test scenario operation adjustment and control method.

[0127] Compared with the prior art, the present invention proposes a multi-objective coordinated intelligent driving test scenario operation adjustment control method, which has the following advantages:

[0128] First, this scheme proposes a road fusion method, which combines the heading angle and heading angle change rate of the road nodes in the road to calculate the road information that characterizes the road form and complexity. The road information is used as the type of road to realize the extraction of different types of key road areas, and a number of key road areas that meet the test target requirements are screened out according to the test target. The screened key road areas are clustered based on the similarity of the road information and the distance between the start and end points of the key road areas. Each road cluster corresponds to a fusion test scene road. The road with the highest degree of fusion is selected as the test scene road to realize the adaptive generation of test scenes based on test targets and real roads.

[0129] At the same time, this scheme constructs a driving trajectory planning objective function based on the path similarity cost, compact cost, trajectory smoothness cost and collision cost of the test vehicle's driving trajectory, and solves the objective function based on the trajectory deviation constraint of the test vehicle's driving trajectory to obtain the test vehicle's driving trajectory of the fusion test scene road, and divides the test vehicle's driving trajectory into several trajectory segments. According to the obstacle information and heading angle of the trajectory segment, the vehicle driving speed of each trajectory segment is dynamically and alternately adjusted to slow down the vehicle speed in areas with many obstacles and complex trajectories, thereby improving driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0130] Figure 1 A flowchart of a multi-objective collaborative intelligent driving test scenario operation adjustment control method provided by an embodiment of the present invention;

[0131] Figure 2 A schematic diagram of the structure of an electronic device for implementing a multi-objective collaborative intelligent driving test scenario operation adjustment control method provided by an embodiment of the present invention;

[0132] In the figure: 1 electronic device, 10 processor, 11 memory, 12 program, 13 communication interface;

[0133] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0134] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0135] The embodiment of the present application provides a multi-target collaborative intelligent driving test scenario operation adjustment control method. The execution subject of the multi-target collaborative intelligent driving test scenario operation adjustment control method includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the multi-target collaborative intelligent driving test scenario operation adjustment control method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0136] Embodiment 1:

[0137] S1: Collect real road map data and identify key road areas to obtain different types of key road areas.

[0138] Collect real road map data, wherein the collected real road map data is represented in the form of:

[0139] ;

[0140] ;

[0141] ;

[0142] ;

[0143] in:

[0144] Indicates the collected real road map data;

[0145] Displays real road map data The initial set of roads in Represents the initial road set The nth initial road in, N represents the initial road set The total number of initial roads in ; the initial roads refer to roads without intersections in the middle of the roads;

[0146] Displays real road map data The set of intersection locations in , Represents a set of intersection locations The mth intersection position in, M represents the intersection position set The total number of intersection locations in ;

[0147] Indicates the initial road In road nodes, among which Indicates the initial road The starting point in Indicates the initial road The end point in the road node includes the turning point and the starting and ending points of the road;

[0148] For the initial road set The key road areas are identified based on the initial roads in the dataset and different types of key road areas are obtained.

[0149] The initial road set The initial road in the process of identifying key road areas includes:

[0150] For the initial road set The critical road area is identified by the initial road in the image. The critical road area identification process is as follows:

[0151] S11: The initial roads whose road lengths are higher than the preset road length threshold are regarded as key road areas to form a key road area set. :

[0152] ;

[0153] ;

[0154] in:

[0155] represents the g-th critical road area, and G represents the total number of critical road areas;

[0156] Indicates critical road areas In road nodes;

[0157] S12: Calculate the critical road area set The road node heading angle sequence of any key road area in The road node heading angle sequence is:

[0158] ;

[0159] ;

[0160] in:

[0161] Indicates critical road areas The road node heading angle sequence;

[0162] Indicates critical road areas The i-th road node The X-axis coordinate value in the Mercator coordinate system, Indicates critical road areas The i-th road node The Y-axis coordinate value in the Mercator coordinate system, ;

[0163] Indicates critical road areas The i-th road node The heading angle of the road node;

[0164] S13: Calculate the key road area set The heading angle change rate sequence of any key road area in The heading angle change rate sequence is:

[0165] ;

[0166] ;

[0167] in:

[0168] Indicates critical road areas The heading angle change rate sequence;

[0169] Indicates critical road areas The i-th road node The rate of change of heading angle;

[0170] Indicates critical road areas The i-th road node In key road areas The relative position of the i-th road node Along key road areas To starting point distance;

[0171] S14: Constitutes a critical road area Road information:

[0172] ;

[0173] ;

[0174] in:

[0175] Indicates critical road areas Road information;

[0176] Indicates critical road areas The heading angle change information, Represents the heading angle change rate sequence The number of road nodes above the preset change rate threshold, as well as Indicates critical road areas If both are close to 0, it means the critical road area is the straight road area. The larger the two are, the more critical the road area is. The higher the degree of curvature and complexity;

[0177] Indicates critical road areas The relative position change sequence.

[0178] S2: Select the corresponding key road area according to the test target, and perform clustering fusion of the key road areas to obtain a fused test scene road.

[0179] In the step S2, the corresponding key road area is selected according to the test target, including:

[0180] Generate the test target of the driving test scenario, where the test target includes the road form and complexity of the test scenario. The road form includes straight roads and curved roads. Select the corresponding key road area according to the test target. The selected key road area set is:

[0181] ;

[0182] in:

[0183] represents the dth key road area selected, and D represents the total number of key road areas selected;

[0184] Key road areas The road information is ;

[0185] The selected key road areas are clustered and fused to obtain a fused test scene road.

[0186] The clustering and fusion of the selected key road areas to obtain a fusion test scene road includes:

[0187] The selected key road areas are clustered and fused to obtain the fused test scene roads, where the clustering fusion process is as follows:

[0188] S21: Calculate the road node correlation distance between any two selected key road areas, where the key road area and The road node association distance is:

[0189] ;

[0190] in:

[0191] Indicates critical road areas and The road node association distance;

[0192] Represents a road node The Euclidean distance between Indicates critical road areas The Road nodes, Indicates critical road areas The road nodes;

[0193] Indicates critical road areas The total number of road nodes in , Indicates critical road areas The total number of road nodes in ;

[0194] S22: Calculate the road information distance between any two selected key road areas, where the key road area and The road information distance is:

[0195] ;

[0196] in:

[0197] Indicates critical road areas and Road information distance;

[0198] represents the L2 norm;

[0199] represents an exponential function with a natural constant as base;

[0200] S23: Construct the distance between any two selected key road areas, where the key road area and The distance is:

[0201] ;

[0202] in:

[0203] Indicates critical road areas and distance;

[0204] S24: Based on the distance between the key road areas, a clustering algorithm is used to cluster the selected D key road areas to obtain U road clusters, the mean of the road node association distance between any two key road areas in any road cluster is calculated, the road cluster with the smallest mean of the road node association distance is selected, and all the key road areas in the selected road cluster are used as the fusion test scene road load. In the embodiment of the present invention, the clustering algorithm used is a hierarchical clustering algorithm.

[0205] S3: According to the starting and ending points of the test vehicle in the fusion test scene road and the fusion test scene road, the driving trajectory of the test vehicle on the fusion test scene road is obtained.

[0206] In the step S3, the test vehicle driving trajectory is generated according to the start and end points of the test vehicle in the fused test scene road and the fused test scene road, including:

[0207] According to the starting and ending points of the test vehicle in the fusion test scene road and the fusion test scene road, the test vehicle driving trajectory is generated, wherein the driving trajectory planning process of the test vehicle on the fusion test scene road Load is as follows:

[0208] S31: Obtain road node information of the fusion test scenario road Load:

[0209] ;

[0210] in:

[0211] Represents the K road node information of the fusion test scenario road load;

[0212] S32: Construct the driving trajectory planning objective function:

[0213] ;

[0214] ;

[0215] ;

[0216] ;

[0217] ;

[0218] in:

[0219] represents the driving trajectory planning objective function, and H represents the driving trajectory of the test vehicle to be solved;

[0220] They represent the path similarity cost, compact cost, trajectory smoothness cost and collision cost of the test vehicle's driving trajectory H respectively;

[0221] Indicates the coordinate position of the kth road node in the fusion test scene road Load, Represents the uth track point in the test vehicle's driving track H The coordinate position of Indicates coordinate position The X-axis coordinate in Indicates coordinate position The Y-axis coordinate in;

[0222] Indicates coordinate position The Euclidean distance between

[0223] represents the adjustment coefficient, Set to 10;

[0224] Indicates coordinate position The Euclidean distance to the nearest obstacle in the fusion test scene road Load, Indicates the preset maximum obstacle impact distance;

[0225] S33: Planning the objective function of the driving trajectory Perform optimization and solve to obtain the test vehicle's driving trajectory .

[0226] In the step S33, the target function of the driving trajectory is planned Perform optimization solutions, including:

[0227] S331: Generate driving trajectory planning objective function Constraints:

[0228] ;

[0229] in:

[0230] represents the trajectory deviation threshold of the test vehicle's driving trajectory;

[0231] S332: Initialize and generate a set of test vehicle driving trajectories , and the iteration coefficient ;

[0232] S333: Set the current iteration number to t, the maximum iteration number to Max, and the initial value of t to 0. Then the t-th iteration results of the test vehicle driving trajectory and iteration coefficient are ;

[0233] in: It represents the iteration coefficient of the t-th iteration, which is used to control the driving trajectory objective function of the t-th iteration;

[0234] S334: Reconstruct the driving trajectory planning objective function based on the constraint conditions, where the reconstruction result is:

[0235] ;

[0236] in:

[0237] Indicates the test vehicle's driving trajectory The coordinate position of the u-th trajectory point in ;

[0238] The reconstructed Find the minimum value and obtain the test vehicle driving trajectory that minimizes the reconstruction result ;

[0239] S335: If If it is less than the preset threshold, The final solution for the test vehicle driving trajectory , otherwise let , t=t+1, return to step S334, where represents the coefficient iteration step size, Set to 0.1, Represents the iteration coefficient of the t+1th iteration.

[0240] S4: According to the calculated driving trajectory of the test vehicle, dynamically and alternately adjust the driving speed of the test vehicle on the driving trajectory.

[0241] In step S4, the driving speed of the test vehicle on the driving track is dynamically and alternately regulated, including:

[0242] The test vehicle is on the driving track The driving speed on the vehicle is dynamically alternatingly regulated, wherein the dynamic alternating regulation process is as follows:

[0243] S41: Obtaining the driving trajectory of the test vehicle Trajectory path segments in :

[0244] ;

[0245] in:

[0246] Indicates the test vehicle's driving trajectory The kth trajectory path segment in , that is, the test vehicle driving trajectory The kth trajectory point And the k+1th trajectory point The trajectory path between

[0247] S42: Calculate the path length, heading angle change information and number of obstacles of each trajectory path segment. The heading angle change information is , the number of obstacles affecting is ; The trajectory path segment The heading angle change information is the trajectory point Testing vehicle driving trajectory The heading angle change rate in the trajectory path segment The influencing obstacle in is the trajectory path segment The driving trajectory of the test vehicle The distance between The number of obstacles;

[0248] S43: Generate a test vehicle driving trajectory Dynamically control the driving speed of different trajectory path segments, where the trajectory path segment The dynamic control driving speed is:

[0249] ;

[0250] in:

[0251] Represents a trajectory path segment Dynamically control driving speed.

[0252] Embodiment 2:

[0253] like Figure 2 , is a schematic diagram of the structure of an electronic device for implementing a method for adjusting and controlling operation of a multi-objective collaborative intelligent driving test scenario provided by an embodiment of the present invention.

[0254] The electronic device 1 may include a processor 10 , a memory 11 , a communication interface 13 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10 , such as a program 12 .

[0255] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 may not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the program 12, etc., but also be used to temporarily store data that has been output or is to be output.

[0256] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as the program 12 for running, regulating, and controlling the intelligent driving test scenario for realizing multi-objective collaboration), and calls the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0257] The communication interface 13 may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices, and to achieve connection and communication between internal components of the electronic device.

[0258] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0259] Figure 2 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 2 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0260] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0261] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0262] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0263] The program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0264] Collect real road map data and identify key road areas to obtain different types of key road areas;

[0265] Select the corresponding key road area according to the test target, and perform clustering fusion of the key road areas to obtain the fusion test scene road;

[0266] According to the starting and ending points of the test vehicle in the fusion test scene road and the fusion test scene road, a driving trajectory of the test vehicle on the fusion test scene road is obtained;

[0267] According to the calculated driving trajectory of the test vehicle, the driving speed of the test vehicle on the driving trajectory is dynamically and alternately regulated.

[0268] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figure 1 to Figure 2 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0269] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0270] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0271] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A multi-objective collaborative intelligent driving test scenario operation adjustment control method, It is characterized in that The method comprises: S1: Collect real road map data and identify key road areas to obtain different types of key road areas; The representation of the collected real road map data is as follows: Road={Road 1 ,Road 2 } Road 1 ={L n |n∈[1,N]} Road 2 ={c m |m∈[1,M]} in: Road represents the collected real road map data; Road 1 Represents the initial road set in the real road map data Road, L n Represents the initial road set Road 1 The nth initial road in , N represents the initial road set Road 1 The total number of initial roads in ; the initial roads refer to roads without intersections in the middle of the roads; Road 2 Represents the intersection location set in the real road map data Road, c m Represents the intersection location set Road 2 The mth intersection position in , where M represents the intersection position set Road 2 The total number of intersection locations in ; represents the initial road L n num n road nodes, among which Indicates the initial road L n The starting point in represents the initial road L n The end point in the road node includes the turning point and the starting and ending points of the road; For the initial road set Road 1 The initial roads in the image are used to identify the key road areas, and different types of key road areas are obtained; S2: Select the corresponding key road area according to the test target, and perform clustering fusion of the key road areas to obtain the fusion test scene road; S3: Obtaining a driving trajectory of the test vehicle on the fusion test scene road according to the starting and ending points of the test vehicle on the fusion test scene road and the fusion test scene road; S4: dynamically and alternately regulating the driving speed of the test vehicle on the driving trajectory according to the calculated driving trajectory of the test vehicle; The initial road set Road 1 The initial road in the process of identifying key road areas includes: For the initial road set Road 1 The critical road area is identified by the initial road in the image. The critical road area identification process is as follows: S11: initial roads whose road lengths are higher than a preset road length threshold are taken as key road areas to form a key road area set Q: Q={Q g |g∈[1,G]} in: Q g represents the g-th critical road area, and G represents the total number of critical road areas; Represents the critical road area Q g NUM in g road nodes; S12: Calculate the road node heading angle sequence of any key road area in the key road area set Q, where the key road area Q g The road node heading angle sequence is: in: r g Represents the critical road area Q g The road node heading angle sequence; Represents the critical road area Q g The i-th road node The X-axis coordinate value in the Mercator coordinate system, Represents the critical road area Q g The i-th road node The Y-axis coordinate value in the Mercator coordinate system, i∈[1,NUM g ]; Represents the critical road area Q g The i-th road node The heading angle of the road node; S13: Calculate and obtain a sequence of heading angle change rates of any key road area in the key road area set Q, where the key road area Q g The heading angle change rate sequence is: in: R g Represents the critical road area Q g The heading angle change rate sequence; Represents the critical road area Q g The i-th road node The rate of change of heading angle; Represents the critical road area Q g The i-th road node In the key road area Q g The relative position of the i-th road node Along the key road area Q g To starting point distance; S14: Constitutes the critical road area Q g Road information: in: F g Represents the critical road area Q g The road information is the road type of the key road area; Represents the critical road area Q g Heading angle change information, Count(R g ) represents the heading angle change rate sequence R g The number of road nodes above the preset change rate threshold, and Count(R g ) represents the critical road area Q g If both are close to 0, it means that the critical road area Q g is the straight road area. The larger the two are, the more critical the road area Q is. g The higher the degree of curvature and complexity; I g Represents the critical road area Q g The relative position change sequence.

2. A multi-objective coordinated intelligent driving test scenario operation adjustment control method as claimed in claim 1, It is characterized in that In the step S2, the corresponding key road area is selected according to the test target, including: Generate test targets for driving test scenarios, where the test targets include the road form and complexity of the test scenario. The road form includes straight roads and curved roads. Select the corresponding key road areas according to the test targets. The selected key road area set is: {Q(d)|d∈[1,D]} in: Q(d) represents the dth key road area selected, and D represents the total number of key road areas selected; The road information of the key road area Q(d) is F(d); The selected key road areas are clustered and fused to obtain a fused test scene road.

3. A multi-objective coordinated intelligent driving test scenario operation adjustment control method as claimed in claim 2, It is characterized in that The clustering and fusion of the selected key road areas to obtain a fusion test scene road includes: The selected key road areas are clustered and fused to obtain the fused test scene roads, where the clustering fusion process is as follows: S21: Calculate the road node correlation distance between any two selected key road areas, where the road node correlation distance between the key road areas Q(d) and Q(s) is: dis 1 (Q(d),Q(s))=min{dis(Q(d,j d ),Q(s,j s ))|j d =1,Num(d);j s =1,Num(s)} in: dis 1 (Q(d),Q(s)) represents the road node association distance between the key road areas Q(d) and Q(s); dis(Q(d,j d ),Q(s,j s )) represents the road node Q(d,j d ),Q(s,j s ), Q(d,j d ) represents the jth critical road region Q(d) d road nodes, Q(s,j s ) represents the jth critical road region Q(s) s road nodes; Num(d) represents the total number of road nodes in the critical road area Q(d), and Num(s) represents the total number of road nodes in the critical road area Q(s); S22: Calculate the road information distance between any two selected key road areas, where the road information distance between the key road areas Q(d) and Q(s) is: in: dis 2 (Q(d),Q(s)) represents the road information distance between the key road areas Q(d) and Q(s); ||·|| 2 represents the L2 norm; exp(·) represents an exponential function with a natural constant as the base; S23: Construct the distance between any two selected key road areas, where the distance between the key road areas Q(d) and Q(s) is: dis(Q(d),Q(s))=dis 1 (Q(d),Q(s))·dis 2 (Q(d),Q(s)) in: dis(Q(d),Q(s)) represents the distance between the critical road areas Q(d) and Q(s); S24: Based on the distance between the key road areas, a clustering algorithm is used to cluster the selected D key road areas to obtain U road clusters, and the mean of the road node association distance between any two key road areas in any road cluster is calculated. The road cluster with the smallest mean of the road node association distance is selected, and all the key road areas in the selected road cluster are used as the fusion test scenario road load.

4. The multi-objective coordinated intelligent driving test scenario operation adjustment control method according to claim 1, It is characterized in that In the step S3, the test vehicle driving trajectory is generated according to the start and end points of the test vehicle in the fused test scene road and the fused test scene road, including: According to the starting and ending points of the test vehicle in the fusion test scene road and the fusion test scene road, the test vehicle driving trajectory is generated, wherein the driving trajectory planning process of the test vehicle on the fusion test scene road Load is as follows: S31: Obtain road node information of the fusion test scenario road Load: Load=(Load 1 ,Load 2 ,...,Load k ,...,Load K ) in: Load 1 ,Load 2 ,...,Load k ,...,Load K Represents the K road node information of the fusion test scene road load; S32: Construct the driving trajectory planning objective function: f(H)=min f 1 (H)+f 2 (H)+f 3 (H)+f 4 (H) in: f(H) represents the driving trajectory planning objective function, and H represents the driving trajectory of the test vehicle to be solved; f 1 (H),f 2 (H),f 3 (H),f 4 (H) represents the path similarity cost, compact cost, trajectory smoothness cost and collision cost of the test vehicle's driving trajectory H respectively; Load k (x, y) represents the coordinate position of the kth road node in the fusion test scene road Load, H u (x,y) represents the u-th trajectory point H in the test vehicle's driving trajectory H u The coordinate position, H u (x) represents the coordinate position H u The X-axis coordinate in (x,y), H u (y) represents the coordinate position H u The Y-axis coordinate in (x,y); DIS(Load k (x,y),H u (x,y)) represents the coordinate position Load k (x,y),H u The Euclidean distance between (x,y); ε represents the adjustment coefficient, and ε is set to 10; Indicates the coordinate position H u (x,y) is the Euclidean distance to the nearest obstacle in the fusion test scene road Load. Indicates the preset maximum obstacle impact distance; S33: Optimize and solve the driving trajectory planning objective function f(H) to obtain the test vehicle driving trajectory 5. A multi-objective coordinated intelligent driving test scenario operation adjustment control method as claimed in claim 4, It is characterized in that In the step S33, the driving trajectory planning objective function f(H) is optimized and solved, including: S331: Generate the constraint conditions of the driving trajectory planning objective function f(H): in: δ represents the trajectory deviation threshold of the test vehicle’s driving trajectory; S332: Initialize and generate a set of test vehicle driving trajectories H 0 , and the iteration coefficient B 0 ; S333: Set the current iteration number to t, the maximum iteration number to Max, and the initial value of t to 0. Then the t-th iteration results of the test vehicle driving trajectory and the iteration coefficient are H t ,B t ; Among them: B t It represents the iteration coefficient of the t-th iteration, which is used to control the driving trajectory objective function of the t-th iteration; S334: Reconstruct the driving trajectory planning objective function based on the constraint conditions, where the reconstruction result is: in: Indicates the test vehicle's driving trajectory H t The coordinate position of the u-th trajectory point in ; For the reconstructed f'(H t ) to find the minimum value and obtain the test vehicle driving trajectory H that makes the reconstruction result reach the minimum t+1 ; S335: If If it is less than the preset threshold, H t+1 The final solution for the test vehicle driving trajectory Otherwise, let B t+1 =γB t , t = t + 1, return to step S334, where γ represents the coefficient iteration step, and γ is set to 0.1, B t+1 Represents the iteration coefficient of the t+1th iteration.

6. The multi-objective coordinated intelligent driving test scenario operation adjustment control method according to claim 1, It is characterized in that In step S4, the driving speed of the test vehicle on the driving track is dynamically and alternately regulated, including: The test vehicle is on the driving track The driving speed on the vehicle is dynamically alternatingly regulated, wherein the dynamic alternating regulation process is as follows: S41: Obtaining the driving trajectory of the test vehicle Trajectory path segments in : (WITH 1 ,WITH 2 ,...,WITH k ,...,WITH K-1 ) in: Z k Indicates the test vehicle's driving trajectory The kth trajectory path segment in , that is, the test vehicle driving trajectory The kth trajectory point and the k+1th trajectory point The trajectory path between S42: Calculate the path length, heading angle change information and number of obstacles of each trajectory path segment, where the trajectory path segment Z k The heading angle change information is Z k (1), the number of obstacles affecting the k (2); The trajectory path segment Z k The heading angle change information is the trajectory point Testing vehicle driving trajectory The heading angle change rate in the trajectory path segment Z k The influencing obstacle in is the trajectory path segment Z k The driving trajectory of the test vehicle The distance between The number of obstacles; S43: Generate a test vehicle driving trajectory Dynamically control the driving speed of different trajectory path segments in the trajectory path segment Z k The dynamic control driving speed is: in: v k Represents the trajectory path segment Z k Dynamically control driving speed.

Images